MEDIQA-CORR@ ClinicalNLP 2024
MEDIQA-CORR @ NAACL-ClinicalNLP 2024
Medical Error Detection & Correction
Motivation
Large language models (LLMs) show promise in being applied on unseen tasks with competitive ability.
However, by construction, such models have a key vulnerability; their ability is only as good as its underlying training data. Since LLMs rely on large corpora of textual data (often from the world wide web) for training, their data is almost impossible to manually curate at scale. If the data contains false information or only one perspective or type of information, the ability of LLMs to discern factual information may be hindered. Also, as a consequence to their own success, some online content may be entirely generated by LLMs that are prone to hallucinated information. In addition, in specialized domains, online information can be unreliable, harmful, and contain logical inconsistencies that may hinder the models' reasoning ability. However, most previous works on common sense detection have focused on the general domain [1-2].
In this task, we seek to address the problem of identifying and correcting (common sense) medical errors in clinical notes. From a human perspective, these errors require medical expertise and knowledge to be both identified and corrected.
[1] SemEval-2020 Task 4: Commonsense Validation and Explanation. Cunxiang Wang, Shuailong Liang, Yili Jin, Yilong Wang, Xiaodan Zhu, Yue Zhang.
[2] CREAK: A Dataset for Commonsense Reasoning over Entity Knowledge. Yasumasa Onoe, Michael J.Q. Zhang, Eunsol Choi, Greg Durrett.
Tasks
Participants will be given a snippet of clinical text and asked to:
Detect whether the text includes a medical error. (Binary Classification)
Identify the text span associated with the error, if a medical error exists. (Span Identification)
Provide a free text correction, if a medical error exists. (Natural Language Generation)
Registration, Datasets & Evaluation
MEDIQA-CORR@Codabench: https://www.codabench.org/competitions/1900/
MEDIQA-CORR@GitHub: https://github.com/abachaa/MEDIQA-CORR-2024
Registration:
Please complete the ClinicalNLP-MEDIQA 2024 registration form first: https://docs.google.com/forms/d/e/1FAIpQLScUnP2TJQX996BR-6dd6GvWAmkfE8VrX135I3VAYuecD1VR9Q/viewform?vc=0&c=0&w=1&flr=0
Download and fill out the Data Usage Agreement (DUA) and send the completed and signed DUA at mediqa.organizers@gmail.com by March 18, 2024, to have access to the UW datasets.
Accept the Terms and Conditions and join the Codabench project: https://www.codabench.org/competitions/1900/
Schedule
All deadlines are 11:59PM UTC-12:00 (anywhere on Earth)
First CFP & Registration opens: Monday January 8, 2024
Training & validation data release: Friday January 26, 2024
Registration ends: Monday March 18, 2024
Test data release: Tuesday March 26, 2024
Run submission due: Thursday March 28, 2024
Code submission due: Friday March 29, 2024 (The GitHub repo URL should be included in the submission form)
Release of the results by the organizers: Monday April 1, 2024
Paper submission period starts: Monday April 8, 2024
Paper submission due: Wednesday April 10, 2024
Notification of acceptance: Thursday April 18, 2024
Final versions of papers due: Wednesday April 24, 2024
ClinicalNLP Workshop @ NAACL 2024: June 21 or 22, 2024, Mexico City, Mexico
Contact
If you have any questions regarding your team's registration, please email us at mediqa.organizers@gmail.com
For more updates or inquiries, join the MEDIQA Google group https://groups.google.com/g/mediqa-nlp and email us at mediqa-nlp@googlegroups.com (mailing list)
Organizers
Asma Ben Abacha, Microsoft, USA
Wen-wai Yim, Microsoft, USA
Meliha Yetisgen, University of Washington, USA
Fei Xia, University of Washington, USA